zmsBERT / manifest.json
doxx9999's picture
Upload manifest.json with huggingface_hub
aadaea4 verified
{
"encoder.embeddings.word_embeddings.weight": {
"shape": [
32035,
768
],
"offset": 0,
"size": 24602880
},
"encoder.embeddings.position_embeddings.weight": {
"shape": [
512,
768
],
"offset": 98411520,
"size": 393216
},
"encoder.embeddings.token_type_embeddings.weight": {
"shape": [
2,
768
],
"offset": 99984384,
"size": 1536
},
"encoder.embeddings.LayerNorm.weight": {
"shape": [
768
],
"offset": 99990528,
"size": 768
},
"encoder.embeddings.LayerNorm.bias": {
"shape": [
768
],
"offset": 99993600,
"size": 768
},
"encoder.encoder.layer.0.attention.self.query.weight": {
"shape": [
768,
768
],
"offset": 99996672,
"size": 589824
},
"encoder.encoder.layer.0.attention.self.query.bias": {
"shape": [
768
],
"offset": 102355968,
"size": 768
},
"encoder.encoder.layer.0.attention.self.key.weight": {
"shape": [
768,
768
],
"offset": 102359040,
"size": 589824
},
"encoder.encoder.layer.0.attention.self.key.bias": {
"shape": [
768
],
"offset": 104718336,
"size": 768
},
"encoder.encoder.layer.0.attention.self.value.weight": {
"shape": [
768,
768
],
"offset": 104721408,
"size": 589824
},
"encoder.encoder.layer.0.attention.self.value.bias": {
"shape": [
768
],
"offset": 107080704,
"size": 768
},
"encoder.encoder.layer.0.attention.output.dense.weight": {
"shape": [
768,
768
],
"offset": 107083776,
"size": 589824
},
"encoder.encoder.layer.0.attention.output.dense.bias": {
"shape": [
768
],
"offset": 109443072,
"size": 768
},
"encoder.encoder.layer.0.attention.output.LayerNorm.weight": {
"shape": [
768
],
"offset": 109446144,
"size": 768
},
"encoder.encoder.layer.0.attention.output.LayerNorm.bias": {
"shape": [
768
],
"offset": 109449216,
"size": 768
},
"encoder.encoder.layer.0.intermediate.dense.weight": {
"shape": [
3072,
768
],
"offset": 109452288,
"size": 2359296
},
"encoder.encoder.layer.0.intermediate.dense.bias": {
"shape": [
3072
],
"offset": 118889472,
"size": 3072
},
"encoder.encoder.layer.0.output.dense.weight": {
"shape": [
768,
3072
],
"offset": 118901760,
"size": 2359296
},
"encoder.encoder.layer.0.output.dense.bias": {
"shape": [
768
],
"offset": 128338944,
"size": 768
},
"encoder.encoder.layer.0.output.LayerNorm.weight": {
"shape": [
768
],
"offset": 128342016,
"size": 768
},
"encoder.encoder.layer.0.output.LayerNorm.bias": {
"shape": [
768
],
"offset": 128345088,
"size": 768
},
"encoder.encoder.layer.1.attention.self.query.weight": {
"shape": [
768,
768
],
"offset": 128348160,
"size": 589824
},
"encoder.encoder.layer.1.attention.self.query.bias": {
"shape": [
768
],
"offset": 130707456,
"size": 768
},
"encoder.encoder.layer.1.attention.self.key.weight": {
"shape": [
768,
768
],
"offset": 130710528,
"size": 589824
},
"encoder.encoder.layer.1.attention.self.key.bias": {
"shape": [
768
],
"offset": 133069824,
"size": 768
},
"encoder.encoder.layer.1.attention.self.value.weight": {
"shape": [
768,
768
],
"offset": 133072896,
"size": 589824
},
"encoder.encoder.layer.1.attention.self.value.bias": {
"shape": [
768
],
"offset": 135432192,
"size": 768
},
"encoder.encoder.layer.1.attention.output.dense.weight": {
"shape": [
768,
768
],
"offset": 135435264,
"size": 589824
},
"encoder.encoder.layer.1.attention.output.dense.bias": {
"shape": [
768
],
"offset": 137794560,
"size": 768
},
"encoder.encoder.layer.1.attention.output.LayerNorm.weight": {
"shape": [
768
],
"offset": 137797632,
"size": 768
},
"encoder.encoder.layer.1.attention.output.LayerNorm.bias": {
"shape": [
768
],
"offset": 137800704,
"size": 768
},
"encoder.encoder.layer.1.intermediate.dense.weight": {
"shape": [
3072,
768
],
"offset": 137803776,
"size": 2359296
},
"encoder.encoder.layer.1.intermediate.dense.bias": {
"shape": [
3072
],
"offset": 147240960,
"size": 3072
},
"encoder.encoder.layer.1.output.dense.weight": {
"shape": [
768,
3072
],
"offset": 147253248,
"size": 2359296
},
"encoder.encoder.layer.1.output.dense.bias": {
"shape": [
768
],
"offset": 156690432,
"size": 768
},
"encoder.encoder.layer.1.output.LayerNorm.weight": {
"shape": [
768
],
"offset": 156693504,
"size": 768
},
"encoder.encoder.layer.1.output.LayerNorm.bias": {
"shape": [
768
],
"offset": 156696576,
"size": 768
},
"encoder.encoder.layer.2.attention.self.query.weight": {
"shape": [
768,
768
],
"offset": 156699648,
"size": 589824
},
"encoder.encoder.layer.2.attention.self.query.bias": {
"shape": [
768
],
"offset": 159058944,
"size": 768
},
"encoder.encoder.layer.2.attention.self.key.weight": {
"shape": [
768,
768
],
"offset": 159062016,
"size": 589824
},
"encoder.encoder.layer.2.attention.self.key.bias": {
"shape": [
768
],
"offset": 161421312,
"size": 768
},
"encoder.encoder.layer.2.attention.self.value.weight": {
"shape": [
768,
768
],
"offset": 161424384,
"size": 589824
},
"encoder.encoder.layer.2.attention.self.value.bias": {
"shape": [
768
],
"offset": 163783680,
"size": 768
},
"encoder.encoder.layer.2.attention.output.dense.weight": {
"shape": [
768,
768
],
"offset": 163786752,
"size": 589824
},
"encoder.encoder.layer.2.attention.output.dense.bias": {
"shape": [
768
],
"offset": 166146048,
"size": 768
},
"encoder.encoder.layer.2.attention.output.LayerNorm.weight": {
"shape": [
768
],
"offset": 166149120,
"size": 768
},
"encoder.encoder.layer.2.attention.output.LayerNorm.bias": {
"shape": [
768
],
"offset": 166152192,
"size": 768
},
"encoder.encoder.layer.2.intermediate.dense.weight": {
"shape": [
3072,
768
],
"offset": 166155264,
"size": 2359296
},
"encoder.encoder.layer.2.intermediate.dense.bias": {
"shape": [
3072
],
"offset": 175592448,
"size": 3072
},
"encoder.encoder.layer.2.output.dense.weight": {
"shape": [
768,
3072
],
"offset": 175604736,
"size": 2359296
},
"encoder.encoder.layer.2.output.dense.bias": {
"shape": [
768
],
"offset": 185041920,
"size": 768
},
"encoder.encoder.layer.2.output.LayerNorm.weight": {
"shape": [
768
],
"offset": 185044992,
"size": 768
},
"encoder.encoder.layer.2.output.LayerNorm.bias": {
"shape": [
768
],
"offset": 185048064,
"size": 768
},
"encoder.encoder.layer.3.attention.self.query.weight": {
"shape": [
768,
768
],
"offset": 185051136,
"size": 589824
},
"encoder.encoder.layer.3.attention.self.query.bias": {
"shape": [
768
],
"offset": 187410432,
"size": 768
},
"encoder.encoder.layer.3.attention.self.key.weight": {
"shape": [
768,
768
],
"offset": 187413504,
"size": 589824
},
"encoder.encoder.layer.3.attention.self.key.bias": {
"shape": [
768
],
"offset": 189772800,
"size": 768
},
"encoder.encoder.layer.3.attention.self.value.weight": {
"shape": [
768,
768
],
"offset": 189775872,
"size": 589824
},
"encoder.encoder.layer.3.attention.self.value.bias": {
"shape": [
768
],
"offset": 192135168,
"size": 768
},
"encoder.encoder.layer.3.attention.output.dense.weight": {
"shape": [
768,
768
],
"offset": 192138240,
"size": 589824
},
"encoder.encoder.layer.3.attention.output.dense.bias": {
"shape": [
768
],
"offset": 194497536,
"size": 768
},
"encoder.encoder.layer.3.attention.output.LayerNorm.weight": {
"shape": [
768
],
"offset": 194500608,
"size": 768
},
"encoder.encoder.layer.3.attention.output.LayerNorm.bias": {
"shape": [
768
],
"offset": 194503680,
"size": 768
},
"encoder.encoder.layer.3.intermediate.dense.weight": {
"shape": [
3072,
768
],
"offset": 194506752,
"size": 2359296
},
"encoder.encoder.layer.3.intermediate.dense.bias": {
"shape": [
3072
],
"offset": 203943936,
"size": 3072
},
"encoder.encoder.layer.3.output.dense.weight": {
"shape": [
768,
3072
],
"offset": 203956224,
"size": 2359296
},
"encoder.encoder.layer.3.output.dense.bias": {
"shape": [
768
],
"offset": 213393408,
"size": 768
},
"encoder.encoder.layer.3.output.LayerNorm.weight": {
"shape": [
768
],
"offset": 213396480,
"size": 768
},
"encoder.encoder.layer.3.output.LayerNorm.bias": {
"shape": [
768
],
"offset": 213399552,
"size": 768
},
"encoder.encoder.layer.4.attention.self.query.weight": {
"shape": [
768,
768
],
"offset": 213402624,
"size": 589824
},
"encoder.encoder.layer.4.attention.self.query.bias": {
"shape": [
768
],
"offset": 215761920,
"size": 768
},
"encoder.encoder.layer.4.attention.self.key.weight": {
"shape": [
768,
768
],
"offset": 215764992,
"size": 589824
},
"encoder.encoder.layer.4.attention.self.key.bias": {
"shape": [
768
],
"offset": 218124288,
"size": 768
},
"encoder.encoder.layer.4.attention.self.value.weight": {
"shape": [
768,
768
],
"offset": 218127360,
"size": 589824
},
"encoder.encoder.layer.4.attention.self.value.bias": {
"shape": [
768
],
"offset": 220486656,
"size": 768
},
"encoder.encoder.layer.4.attention.output.dense.weight": {
"shape": [
768,
768
],
"offset": 220489728,
"size": 589824
},
"encoder.encoder.layer.4.attention.output.dense.bias": {
"shape": [
768
],
"offset": 222849024,
"size": 768
},
"encoder.encoder.layer.4.attention.output.LayerNorm.weight": {
"shape": [
768
],
"offset": 222852096,
"size": 768
},
"encoder.encoder.layer.4.attention.output.LayerNorm.bias": {
"shape": [
768
],
"offset": 222855168,
"size": 768
},
"encoder.encoder.layer.4.intermediate.dense.weight": {
"shape": [
3072,
768
],
"offset": 222858240,
"size": 2359296
},
"encoder.encoder.layer.4.intermediate.dense.bias": {
"shape": [
3072
],
"offset": 232295424,
"size": 3072
},
"encoder.encoder.layer.4.output.dense.weight": {
"shape": [
768,
3072
],
"offset": 232307712,
"size": 2359296
},
"encoder.encoder.layer.4.output.dense.bias": {
"shape": [
768
],
"offset": 241744896,
"size": 768
},
"encoder.encoder.layer.4.output.LayerNorm.weight": {
"shape": [
768
],
"offset": 241747968,
"size": 768
},
"encoder.encoder.layer.4.output.LayerNorm.bias": {
"shape": [
768
],
"offset": 241751040,
"size": 768
},
"encoder.encoder.layer.5.attention.self.query.weight": {
"shape": [
768,
768
],
"offset": 241754112,
"size": 589824
},
"encoder.encoder.layer.5.attention.self.query.bias": {
"shape": [
768
],
"offset": 244113408,
"size": 768
},
"encoder.encoder.layer.5.attention.self.key.weight": {
"shape": [
768,
768
],
"offset": 244116480,
"size": 589824
},
"encoder.encoder.layer.5.attention.self.key.bias": {
"shape": [
768
],
"offset": 246475776,
"size": 768
},
"encoder.encoder.layer.5.attention.self.value.weight": {
"shape": [
768,
768
],
"offset": 246478848,
"size": 589824
},
"encoder.encoder.layer.5.attention.self.value.bias": {
"shape": [
768
],
"offset": 248838144,
"size": 768
},
"encoder.encoder.layer.5.attention.output.dense.weight": {
"shape": [
768,
768
],
"offset": 248841216,
"size": 589824
},
"encoder.encoder.layer.5.attention.output.dense.bias": {
"shape": [
768
],
"offset": 251200512,
"size": 768
},
"encoder.encoder.layer.5.attention.output.LayerNorm.weight": {
"shape": [
768
],
"offset": 251203584,
"size": 768
},
"encoder.encoder.layer.5.attention.output.LayerNorm.bias": {
"shape": [
768
],
"offset": 251206656,
"size": 768
},
"encoder.encoder.layer.5.intermediate.dense.weight": {
"shape": [
3072,
768
],
"offset": 251209728,
"size": 2359296
},
"encoder.encoder.layer.5.intermediate.dense.bias": {
"shape": [
3072
],
"offset": 260646912,
"size": 3072
},
"encoder.encoder.layer.5.output.dense.weight": {
"shape": [
768,
3072
],
"offset": 260659200,
"size": 2359296
},
"encoder.encoder.layer.5.output.dense.bias": {
"shape": [
768
],
"offset": 270096384,
"size": 768
},
"encoder.encoder.layer.5.output.LayerNorm.weight": {
"shape": [
768
],
"offset": 270099456,
"size": 768
},
"encoder.encoder.layer.5.output.LayerNorm.bias": {
"shape": [
768
],
"offset": 270102528,
"size": 768
},
"encoder.encoder.layer.6.attention.self.query.weight": {
"shape": [
768,
768
],
"offset": 270105600,
"size": 589824
},
"encoder.encoder.layer.6.attention.self.query.bias": {
"shape": [
768
],
"offset": 272464896,
"size": 768
},
"encoder.encoder.layer.6.attention.self.key.weight": {
"shape": [
768,
768
],
"offset": 272467968,
"size": 589824
},
"encoder.encoder.layer.6.attention.self.key.bias": {
"shape": [
768
],
"offset": 274827264,
"size": 768
},
"encoder.encoder.layer.6.attention.self.value.weight": {
"shape": [
768,
768
],
"offset": 274830336,
"size": 589824
},
"encoder.encoder.layer.6.attention.self.value.bias": {
"shape": [
768
],
"offset": 277189632,
"size": 768
},
"encoder.encoder.layer.6.attention.output.dense.weight": {
"shape": [
768,
768
],
"offset": 277192704,
"size": 589824
},
"encoder.encoder.layer.6.attention.output.dense.bias": {
"shape": [
768
],
"offset": 279552000,
"size": 768
},
"encoder.encoder.layer.6.attention.output.LayerNorm.weight": {
"shape": [
768
],
"offset": 279555072,
"size": 768
},
"encoder.encoder.layer.6.attention.output.LayerNorm.bias": {
"shape": [
768
],
"offset": 279558144,
"size": 768
},
"encoder.encoder.layer.6.intermediate.dense.weight": {
"shape": [
3072,
768
],
"offset": 279561216,
"size": 2359296
},
"encoder.encoder.layer.6.intermediate.dense.bias": {
"shape": [
3072
],
"offset": 288998400,
"size": 3072
},
"encoder.encoder.layer.6.output.dense.weight": {
"shape": [
768,
3072
],
"offset": 289010688,
"size": 2359296
},
"encoder.encoder.layer.6.output.dense.bias": {
"shape": [
768
],
"offset": 298447872,
"size": 768
},
"encoder.encoder.layer.6.output.LayerNorm.weight": {
"shape": [
768
],
"offset": 298450944,
"size": 768
},
"encoder.encoder.layer.6.output.LayerNorm.bias": {
"shape": [
768
],
"offset": 298454016,
"size": 768
},
"encoder.encoder.layer.7.attention.self.query.weight": {
"shape": [
768,
768
],
"offset": 298457088,
"size": 589824
},
"encoder.encoder.layer.7.attention.self.query.bias": {
"shape": [
768
],
"offset": 300816384,
"size": 768
},
"encoder.encoder.layer.7.attention.self.key.weight": {
"shape": [
768,
768
],
"offset": 300819456,
"size": 589824
},
"encoder.encoder.layer.7.attention.self.key.bias": {
"shape": [
768
],
"offset": 303178752,
"size": 768
},
"encoder.encoder.layer.7.attention.self.value.weight": {
"shape": [
768,
768
],
"offset": 303181824,
"size": 589824
},
"encoder.encoder.layer.7.attention.self.value.bias": {
"shape": [
768
],
"offset": 305541120,
"size": 768
},
"encoder.encoder.layer.7.attention.output.dense.weight": {
"shape": [
768,
768
],
"offset": 305544192,
"size": 589824
},
"encoder.encoder.layer.7.attention.output.dense.bias": {
"shape": [
768
],
"offset": 307903488,
"size": 768
},
"encoder.encoder.layer.7.attention.output.LayerNorm.weight": {
"shape": [
768
],
"offset": 307906560,
"size": 768
},
"encoder.encoder.layer.7.attention.output.LayerNorm.bias": {
"shape": [
768
],
"offset": 307909632,
"size": 768
},
"encoder.encoder.layer.7.intermediate.dense.weight": {
"shape": [
3072,
768
],
"offset": 307912704,
"size": 2359296
},
"encoder.encoder.layer.7.intermediate.dense.bias": {
"shape": [
3072
],
"offset": 317349888,
"size": 3072
},
"encoder.encoder.layer.7.output.dense.weight": {
"shape": [
768,
3072
],
"offset": 317362176,
"size": 2359296
},
"encoder.encoder.layer.7.output.dense.bias": {
"shape": [
768
],
"offset": 326799360,
"size": 768
},
"encoder.encoder.layer.7.output.LayerNorm.weight": {
"shape": [
768
],
"offset": 326802432,
"size": 768
},
"encoder.encoder.layer.7.output.LayerNorm.bias": {
"shape": [
768
],
"offset": 326805504,
"size": 768
},
"encoder.encoder.layer.8.attention.self.query.weight": {
"shape": [
768,
768
],
"offset": 326808576,
"size": 589824
},
"encoder.encoder.layer.8.attention.self.query.bias": {
"shape": [
768
],
"offset": 329167872,
"size": 768
},
"encoder.encoder.layer.8.attention.self.key.weight": {
"shape": [
768,
768
],
"offset": 329170944,
"size": 589824
},
"encoder.encoder.layer.8.attention.self.key.bias": {
"shape": [
768
],
"offset": 331530240,
"size": 768
},
"encoder.encoder.layer.8.attention.self.value.weight": {
"shape": [
768,
768
],
"offset": 331533312,
"size": 589824
},
"encoder.encoder.layer.8.attention.self.value.bias": {
"shape": [
768
],
"offset": 333892608,
"size": 768
},
"encoder.encoder.layer.8.attention.output.dense.weight": {
"shape": [
768,
768
],
"offset": 333895680,
"size": 589824
},
"encoder.encoder.layer.8.attention.output.dense.bias": {
"shape": [
768
],
"offset": 336254976,
"size": 768
},
"encoder.encoder.layer.8.attention.output.LayerNorm.weight": {
"shape": [
768
],
"offset": 336258048,
"size": 768
},
"encoder.encoder.layer.8.attention.output.LayerNorm.bias": {
"shape": [
768
],
"offset": 336261120,
"size": 768
},
"encoder.encoder.layer.8.intermediate.dense.weight": {
"shape": [
3072,
768
],
"offset": 336264192,
"size": 2359296
},
"encoder.encoder.layer.8.intermediate.dense.bias": {
"shape": [
3072
],
"offset": 345701376,
"size": 3072
},
"encoder.encoder.layer.8.output.dense.weight": {
"shape": [
768,
3072
],
"offset": 345713664,
"size": 2359296
},
"encoder.encoder.layer.8.output.dense.bias": {
"shape": [
768
],
"offset": 355150848,
"size": 768
},
"encoder.encoder.layer.8.output.LayerNorm.weight": {
"shape": [
768
],
"offset": 355153920,
"size": 768
},
"encoder.encoder.layer.8.output.LayerNorm.bias": {
"shape": [
768
],
"offset": 355156992,
"size": 768
},
"encoder.encoder.layer.9.attention.self.query.weight": {
"shape": [
768,
768
],
"offset": 355160064,
"size": 589824
},
"encoder.encoder.layer.9.attention.self.query.bias": {
"shape": [
768
],
"offset": 357519360,
"size": 768
},
"encoder.encoder.layer.9.attention.self.key.weight": {
"shape": [
768,
768
],
"offset": 357522432,
"size": 589824
},
"encoder.encoder.layer.9.attention.self.key.bias": {
"shape": [
768
],
"offset": 359881728,
"size": 768
},
"encoder.encoder.layer.9.attention.self.value.weight": {
"shape": [
768,
768
],
"offset": 359884800,
"size": 589824
},
"encoder.encoder.layer.9.attention.self.value.bias": {
"shape": [
768
],
"offset": 362244096,
"size": 768
},
"encoder.encoder.layer.9.attention.output.dense.weight": {
"shape": [
768,
768
],
"offset": 362247168,
"size": 589824
},
"encoder.encoder.layer.9.attention.output.dense.bias": {
"shape": [
768
],
"offset": 364606464,
"size": 768
},
"encoder.encoder.layer.9.attention.output.LayerNorm.weight": {
"shape": [
768
],
"offset": 364609536,
"size": 768
},
"encoder.encoder.layer.9.attention.output.LayerNorm.bias": {
"shape": [
768
],
"offset": 364612608,
"size": 768
},
"encoder.encoder.layer.9.intermediate.dense.weight": {
"shape": [
3072,
768
],
"offset": 364615680,
"size": 2359296
},
"encoder.encoder.layer.9.intermediate.dense.bias": {
"shape": [
3072
],
"offset": 374052864,
"size": 3072
},
"encoder.encoder.layer.9.output.dense.weight": {
"shape": [
768,
3072
],
"offset": 374065152,
"size": 2359296
},
"encoder.encoder.layer.9.output.dense.bias": {
"shape": [
768
],
"offset": 383502336,
"size": 768
},
"encoder.encoder.layer.9.output.LayerNorm.weight": {
"shape": [
768
],
"offset": 383505408,
"size": 768
},
"encoder.encoder.layer.9.output.LayerNorm.bias": {
"shape": [
768
],
"offset": 383508480,
"size": 768
},
"encoder.encoder.layer.10.attention.self.query.weight": {
"shape": [
768,
768
],
"offset": 383511552,
"size": 589824
},
"encoder.encoder.layer.10.attention.self.query.bias": {
"shape": [
768
],
"offset": 385870848,
"size": 768
},
"encoder.encoder.layer.10.attention.self.key.weight": {
"shape": [
768,
768
],
"offset": 385873920,
"size": 589824
},
"encoder.encoder.layer.10.attention.self.key.bias": {
"shape": [
768
],
"offset": 388233216,
"size": 768
},
"encoder.encoder.layer.10.attention.self.value.weight": {
"shape": [
768,
768
],
"offset": 388236288,
"size": 589824
},
"encoder.encoder.layer.10.attention.self.value.bias": {
"shape": [
768
],
"offset": 390595584,
"size": 768
},
"encoder.encoder.layer.10.attention.output.dense.weight": {
"shape": [
768,
768
],
"offset": 390598656,
"size": 589824
},
"encoder.encoder.layer.10.attention.output.dense.bias": {
"shape": [
768
],
"offset": 392957952,
"size": 768
},
"encoder.encoder.layer.10.attention.output.LayerNorm.weight": {
"shape": [
768
],
"offset": 392961024,
"size": 768
},
"encoder.encoder.layer.10.attention.output.LayerNorm.bias": {
"shape": [
768
],
"offset": 392964096,
"size": 768
},
"encoder.encoder.layer.10.intermediate.dense.weight": {
"shape": [
3072,
768
],
"offset": 392967168,
"size": 2359296
},
"encoder.encoder.layer.10.intermediate.dense.bias": {
"shape": [
3072
],
"offset": 402404352,
"size": 3072
},
"encoder.encoder.layer.10.output.dense.weight": {
"shape": [
768,
3072
],
"offset": 402416640,
"size": 2359296
},
"encoder.encoder.layer.10.output.dense.bias": {
"shape": [
768
],
"offset": 411853824,
"size": 768
},
"encoder.encoder.layer.10.output.LayerNorm.weight": {
"shape": [
768
],
"offset": 411856896,
"size": 768
},
"encoder.encoder.layer.10.output.LayerNorm.bias": {
"shape": [
768
],
"offset": 411859968,
"size": 768
},
"encoder.encoder.layer.11.attention.self.query.weight": {
"shape": [
768,
768
],
"offset": 411863040,
"size": 589824
},
"encoder.encoder.layer.11.attention.self.query.bias": {
"shape": [
768
],
"offset": 414222336,
"size": 768
},
"encoder.encoder.layer.11.attention.self.key.weight": {
"shape": [
768,
768
],
"offset": 414225408,
"size": 589824
},
"encoder.encoder.layer.11.attention.self.key.bias": {
"shape": [
768
],
"offset": 416584704,
"size": 768
},
"encoder.encoder.layer.11.attention.self.value.weight": {
"shape": [
768,
768
],
"offset": 416587776,
"size": 589824
},
"encoder.encoder.layer.11.attention.self.value.bias": {
"shape": [
768
],
"offset": 418947072,
"size": 768
},
"encoder.encoder.layer.11.attention.output.dense.weight": {
"shape": [
768,
768
],
"offset": 418950144,
"size": 589824
},
"encoder.encoder.layer.11.attention.output.dense.bias": {
"shape": [
768
],
"offset": 421309440,
"size": 768
},
"encoder.encoder.layer.11.attention.output.LayerNorm.weight": {
"shape": [
768
],
"offset": 421312512,
"size": 768
},
"encoder.encoder.layer.11.attention.output.LayerNorm.bias": {
"shape": [
768
],
"offset": 421315584,
"size": 768
},
"encoder.encoder.layer.11.intermediate.dense.weight": {
"shape": [
3072,
768
],
"offset": 421318656,
"size": 2359296
},
"encoder.encoder.layer.11.intermediate.dense.bias": {
"shape": [
3072
],
"offset": 430755840,
"size": 3072
},
"encoder.encoder.layer.11.output.dense.weight": {
"shape": [
768,
3072
],
"offset": 430768128,
"size": 2359296
},
"encoder.encoder.layer.11.output.dense.bias": {
"shape": [
768
],
"offset": 440205312,
"size": 768
},
"encoder.encoder.layer.11.output.LayerNorm.weight": {
"shape": [
768
],
"offset": 440208384,
"size": 768
},
"encoder.encoder.layer.11.output.LayerNorm.bias": {
"shape": [
768
],
"offset": 440211456,
"size": 768
},
"encoder.pooler.dense.weight": {
"shape": [
768,
768
],
"offset": 440214528,
"size": 589824
},
"encoder.pooler.dense.bias": {
"shape": [
768
],
"offset": 442573824,
"size": 768
},
"classifier.1.weight": {
"shape": [
256,
768
],
"offset": 442576896,
"size": 196608
},
"classifier.1.bias": {
"shape": [
256
],
"offset": 443363328,
"size": 256
},
"classifier.4.weight": {
"shape": [
11,
256
],
"offset": 443364352,
"size": 2816
},
"classifier.4.bias": {
"shape": [
11
],
"offset": 443375616,
"size": 11
}
}